None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.
Ads Video Skill
Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.
3D Science Explainer Video Skill
Convert scientific concepts into stunning 3D explain animations
Feedback
freeTrialImage.bannerPity
freeTrialImage.upgradeUnlock
- ✓freeTrialImage.benefitHd
- ✓freeTrialImage.benefitWatermark
- ✓freeTrialImage.benefitUnlimited
Haiku 5.5 Benchmark
Source-checked Claude Haiku 5.5 benchmark results: launch scores, price bands and published limits, with clear caveats and retrieval dates.
All Tools
Discover our comprehensive AI-powered animation toolkit
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.
Seedance 2.0
The Future of AI Video Is Here.
FLUX 3 Video Generator
Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator
Seedance 2.0
The Future of AI Video Is Here.
Why These Claude Haiku 5.5 Figures Matter
Launch scores, pricing tiers and effort-based costs are presented alongside their test settings and source dates.
- How Launch Scores Should Be InterpretedElo, partial-credit, coding and accuracy results rely on different scales, so averaging them would be misleading.
- Cost Efficiency for High-Volume TasksDesigned for extraction, classification and summarization jobs run at thousands of repetitions.
- Two Limits That Reshape the TablesLow rates end at 100K tokens, and the 72.4% computer-use figure is partial credit rather than a strict pass rate.
Turning Claude Haiku 5.5 Data into Decisions
Use three practical steps to translate published Claude Haiku 5.5 figures into a workload choice.
Claude Haiku 5.5: What the Data Shows
Specifications, pricing tiers, coding outcomes, computer-use figures and third-party index data for Claude Haiku 5.5.
Context and Output Limits
Text and image inputs produce text output with adaptive thinking enabled. A 1M-token context and 128K-token output ceiling far exceed Haiku 4.5's 200K and 64K.
Pricing Split by Prompt Length
Above 100K prompt tokens, input, output and caching each move to a tier five times the low-cost rate. OpenAI's base Standard tier reaches 272K input tokens.
Terminal-Bench 4.0 Task Completion
Its 39.2% launch result is well ahead of Luna yet below the listed Sol entries. Agent runs allow eight hours, while 2.1 and 3.0 figures come from an earlier experiment.
FrontierCode Quality and Effort Spend
Scoring weighs correctness, tests, scope, style and repository conventions. Haiku reaches 46.4% at max effort and 41.6% at medium for $0.13 per rollout; moving from xhigh to max doubles cost for half a point.
OSWorld 2.1: Partial vs. Strict Success
The run covers 82 offline tasks with five tries each, 1080p screenshots and a 500-step cap. For workflows that must complete, the 37.1% strict rate is the realistic figure.
Third-Party Index and Tool Gains
Artificial Analysis lists Haiku across five effort levels on Intelligence Index v4.3.2 with rounded task costs. HLE scores 45.9% without tools and 57.4% with them, a lift driven by the surrounding system.
Claude Haiku 5.5: Common Questions
Answers to frequent questions about Claude Haiku 5.5 evaluation results, pricing tiers and published limits.
How does Claude Haiku 5.5 stack up against GPT-6 Luna and GPT-6 Sol?
For knowledge work, screenshot handling and narrow coding, Haiku matches Luna in several areas. Sol and Sol 6.1 cost more and justify it on coding, while Sonnet 5.5 remains ahead on most rows.
Why doesn't the 72.4% computer-use figure equal a success rate?
The same evaluation falls to 37.1% when all checkpoints must pass. An agent may find and edit the correct file, then save it in the wrong format or stop before the final step. Include an end-state check.
At what point does Claude Haiku 5.5 move to the higher price tier?
The lowest rates apply only to prompts up to 100K tokens; beyond that, every category costs five times as much. Anthropic's 90%, 50% and roughly 75% savings numbers use different baselines.
Can Claude Haiku 5.5 run locally, and what GPU memory would it require?
Published specifications omit parameter count, active parameters, layer count and training compute. 'Small' describes a product tier rather than an architecture, so local GPU estimates lack a basis.
Does higher reasoning effort always produce better results?
No. Sol 6.1 performs better at medium than at max, and Haiku's 0.2-point lead over Sonnet at max is too small to count as a win. More effort adds tokens, latency and opportunities to drift off task.
Why do identical models appear with different numbers across tables?
Sonnet shows 70.6% in Anthropic's launch table but 61.8% in the public leaderboard snapshot, where Haiku had no visible row. Artificial Analysis removed its 'Default Fallback' label, while Anthropic's migration guide still states that no server-side fallback exists.
Put Claude Haiku 5.5 to Work on Your Use Case
Choose a single workload, set the effort level and compare Claude Haiku 5.5 with your own quality threshold.